Accession Number:

AD1064210

Title:

Learning Mixed Membership Community Models in Social Tagging Networks through Tensor Methods

Descriptive Note:

Technical Report

Corporate Author:

University of California - Irvine Irvine United States

Personal Author(s):

• Anandkumar,Anima
• Sedghi,Hanie

Report Date:

2015-07-18

Pagination or Media Count:

29.0

Abstract:

Community detection in graphs has been extensively studied both in theory and in applications. However, detecting communities in hypergraphs is more challenging. In this paper, we propose a tensor decomposition approach for guaranteed learning of communities in a special class of hypergraphs modeling social tagging systems or folksonomies. A folksonomy is a tripartite 3-uniform hypergraph consisting of user, tag, resource hyperedges. We posit a probabilistic mixed membership community model, and prove that the tensor method consistently learns the communities under efficient sample complexity and separation requirements.

Descriptors:

• machine learning
• models
• random variables
• probabilistic models
• eigenvalues
• decomposition
• communities
• eigenvectors
• inequalities
• networks
• standards
• algorithms
• clustering

Subject Categories:

• Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE